We present ROBO, a model and its companion code for the study of the
interstellar medium (ISM). The aim is to provide an accurate
description of the physical evolution of the ISM and to set the ground
for an ancillary tool to be inserted in NB-TSPH simulations of large
scale structures in cosmological context or of the formation and
evolution of individual galaxies.

The ISM is made of gas and dust. The gas chemical composition is
regulated by a network of reactions that includes a large number of
species.  The dust contains the standard mixture of carbonaceous
grains (graphite grains and PAHs) and silicates of which the model
follows the formation and destruction by several processes. The model
takes into account an accurate treatment of the heating and cooling
processes based on several physical mechanisms.

The model is applied to a wide range of the input parameters and the
results for important quantities describing the physical state of the
gas and dust are presented. The results then are organized in a
database which represents the space of initial and final values of the
parameters after a certain time interval is elapsed.  It constitutes a
sort of vector field representing the evolution of a ISM element under
a large variety of physical conditions.

The database is fed to an artificial neural network (MANN) which, once
trained, yields the same results as ROBO. 

Finally, MANN is faced with the NB-TSPH code EVOL so that the physical
conditions of the ISM can be known at each time and position with a
great accuracy in practice at no computational cost. A few
illustrative cases are presented. We suggest that such an algorithm
can replace the tedious real-time calculations of the thermo-dynamical
properties of the ISM in hydrodynamical codes.